paper-with-me

Papers

The Tool Illusion: Rethinking Tool Use in Web Agents

2026-04-03 · Renze Lou, Baolin Peng, Wenlin Yao, Qianhui Wu, Hao Cheng, Suman Nath, Wenpeng Yin, Jianfeng Gao arxiv

As web agents rapidly evolve, an increasing body of work has moved beyond conventional atomic browser interactions and explored tool use as a higher-level action paradigm. Although prior studies have shown the promise of tools, their conclusions are often drawn from limited experimental scales and sometimes non-comparable settings. As a result, several fundamental questions remain unclear: i) whether tools provide consistent gains for web agents, ii) what practical design principles characterize effective tools, and iii) what side effects tool use may introduce. To establish a stronger empirical foundation for future research, we revisit tool use in web agents through an extensive and carefully controlled study across diverse tool sources, backbone models, tool-use frameworks, and evaluation benchmarks. Our findings both revise some prior conclusions and complement others with broader evidence. We hope this study provides a more reliable empirical basis and inspires future research on tool-use web agents.

📄 PDF Abstract BibTeX arXiv:2604.03465

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Color Visual Illusions: A Statistics-based Computational Model

2020-05-18 · NeurIPS 2020 12 · Elad Hirsch, Ayellet Tal

Visual illusions may be explained by the likelihood of patches in real-world images, as argued by input-driven paradigms in Neuro-Science. However, neither the data nor the tools existed in the past to extensively suppor…

model

Seeing the Evidence, Missing the Answer: Tool-Guided Vision-Language Models on Visual Illusions

2026-03-31 · Xuesong Wang, Harry Wang arxiv

Vision-language models (VLMs) exhibit a systematic bias when confronted with classic optical illusions: they overwhelmingly predict the illusion as "real" regardless of whether the image has been counterfactually modifie…

Image ManipulationSpatial ReasoningImage Compression

How Adversarial Environments Mislead Agentic AI?

2026-04-20 · Zhonghao Zhan, Huichi Zhou, Zhenhao Li, Peiyuan Jing 외 arxiv

Tool-integrated agents are deployed on the premise that external tools ground their outputs in reality. Yet this very reliance creates a critical attack surface. Current evaluations benchmark capability in benign setting…

Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents

2026-02-02 · Zeping Li, Hongru Wang, Yiwen Zhao, Guanhua Chen 외 arxiv

Tool-using agents based on Large Language Models (LLMs) excel in tasks such as mathematical reasoning and multi-hop question answering. However, in long trajectories, agents often trigger excessive and low-quality tool c…

Multi-hop Question AnsweringMathematical Reasoning

Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents

2026-05-25 · Dong-Hee Kim, Reuben Tan, Donghyun Kim arxiv

Visual agents employ external visual tools within visual chains of thought to incorporate fine-grained evidence. While prior work has mainly studied these tools in visual search tasks, their role in more complex visual r…

Visual Question AnsweringSpatial ReasoningVisual Reasoning